© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 3461
    Prev
    Next
    INDEX
    Explanations

    session start or variable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    zig
    -0.10
    iej
    -0.10
     Boh
    -0.10
    ted
    -0.10
     medios
    -0.09
     exce
    -0.09
    лад
    -0.09
     Cousins
    -0.09
    zers
    -0.09
    ailable
    -0.08
    POSITIVE LOGITS
     Session
    0.19
    (Session
    0.18
     session
    0.18
    .Session
    0.18
     sessions
    0.17
     getSession
    0.15
     SESSION
    0.15
     Sessions
    0.15
    /session
    0.15
     sess
    0.14
    Activations Density 0.048%

    No Known Activations